Monitoring and analyzing potato movement dynamics in a chain digger using smart sensing techniques
Measurement: Journal of the International Measurement Confederation, cilt.291, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 291
- Basım Tarihi: 2026
- Doi Numarası: 10.1016/j.measurement.2026.123134
- Dergi Adı: Measurement: Journal of the International Measurement Confederation
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Academic Search Ultimate (EBSCO), Engineering Source (EBSCO), Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Anahtar Kelimeler: ANNs, Automated potato digging, Bruising reduction, Electronic tuber, Reverse control
- Erciyes Üniversitesi Adresli: Evet
Özet
Tubers are very sensitive when they are knocked or shattered by mechanized digging; hence, there is a delicate balance between the efficiency of soil cleaning and factors that may result in damage. This study aims to design an intelligent inverse advisory system that separates these two conflicting objectives. The electronic tuber was used to measure the dynamic behaviour of shock and triaxial vibration in a potato digger with variable speed of tractor power take-off shaft rotation (540, 1000 rpm) and different angles of inclination of the chain conveyor (6.4°, 8.8°, 10.8°). The Kruskal-Wallis test shows that the angle of inclination is the key variable affecting the integrity of the tuber in the physical world, with 8.8° being the best-performing angle among the tested discrete settings to achieve a balance between smooth flow (Yrms) and kinetic energy control (K.E.). However, one can notice an additional intriguing mechanical property stating that the increase in the rotational speed will lead to an increase in the effectiveness of the cleaning process without a corresponding linear increase in the peak acceleration due to the floating frequency effect. It was possible to create four ANNs based on the above facts. The resulting model was highly accurate in predicting impact severity with R2 = 93.8%, while the inverse advisor model could determine optimal operating angles with an error that did not exceed mechanical tolerance (MAE 0.15).